Sistem Kontrol Kesuburan Tanaman Hidroponik Otomatis Menggunakan Artificial Neural Network

Abstract

The COVID-19 pandemic increased the popularity of hydroponic gardening, but it remains challenging for beginners due to the need for precise control of plant conditions. This study develops an automatic hydroponic plant fertility control system using Artificial Neural Network (ANN) to monitor and optimize the growth of lettuce, pakcoy, and spinach. Utilizing sensors, Arduino UNO, Azure Cloud, and Python, the system automates monitoring and notification through Telegram. Testing shows a productivity increase of 13.91% in leaves and 15.28% in stems using the optimized ANN algorithm. Additionally, the System Usability Scale (SUS) evaluation indicates user satisfaction with the system.